Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1216 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2638. Min Act: -0.1700

Data Index: 104276 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2480. Min Act: -0.1700

Data Index: 492529 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2480. Min Act: -0.1700

Data Index: 170658 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1009285 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1258876 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1285231 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2323. Min Act: -0.1700

Data Index: 629364 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2166. Min Act: -0.1700

Data Index: 970787 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2166. Min Act: -0.1700

Data Index: 1171991 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2009. Min Act: -0.1700

Data Index: 481034 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2166. Min Act: -0.1700

Data Index: 705954 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2009. Min Act: -0.1700

Data Index: 63888 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.1851. Min Act: -0.1700

Data Index: 17029 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.1851. Min Act: -0.1700

Data Index: 127845 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.2009. Min Act: -0.1700

Data Index: 360358 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.1851. Min Act: -0.1700

Data Index: 259626 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.1851. Min Act: -0.1700

Data Index: 435788 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.1694. Min Act: -0.1700

Data Index: 259845 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.1851. Min Act: -0.1700

Data Index: 253840 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.2638. Min Range: -3.2638

Max Act: 3.1851. Min Act: -0.1700

Data Index: 671501 (C4 (Web Text))

Max Activating Token Index: 98